© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13691
    Prev
    Next
    INDEX
    Explanations

    depolarization-related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķ°éĩı为
    -0.07
    ãĤ¯ãĤ¿ãĥ¼
    -0.07
    biet
    -0.07
    над
    -0.07
    cket
    -0.07
     fatalities
    -0.06
     Jet
    -0.06
    ä¸įæīĵ
    -0.06
    麻çĥ¦äºĨ
    -0.06
     arity
    -0.06
    POSITIVE LOGITS
     stimulus
    0.08
    åºķèī²
    0.08
    AttributeName
    0.08
    çļĦçĶµ
    0.07
    ä¸Ģä¸ĭ
    0.07
    诱
    0.07
    ienes
    0.07
     elect
    0.07
     volts
    0.07
    çĶµä½į
    0.07
    Activations Density 0.017%

    No Known Activations